Abram
> ☝️ requires fixing ? Nope, it doesn't.
> This can't go to QA until we fix the issue whereby the LLM doesn't respond in numeric format anymore. -- @mmabrouk @aybruhm It works now, and I didn’t change...
**QA Report:** https://agenta-hq.slack.com/archives/C05JT3NQB1R/p1724832222331489?thread_ts=1724757298.386189&cid=C05JT3NQB1R
**QA Report:** https://agenta-hq.slack.com/archives/C05JT3NQB1R/p1724833122715339?thread_ts=1724757298.386189&cid=C05JT3NQB1R
> ☝️ requires fixing ? Nope, it doesn't.
> Thanks @aybruhm, quick question 👇 Shouldn't this apply to all non-RAG evaluators (not just `contains_json`) ? We already are doing that. The `contains_json` evaluator requires that the value of...
@jp-agenta, as per our discussion, the PR has been updated. Here’s a preview of what it looks like: 
### Failing CLI Command Tests / Serve-to-OSS: The failing test is due to a missing schema migration in OSS production.  ### CLI Commands Working Locally:  ### Next Steps:...
> What is the QA status for this? PR description updated with acceptance tests, and have been handed over to @zenUnicorn for QA.
> @aybruhm It is expected that the oss tests fail here, since they are using the old backend hosted in oss.agenta.ai (which expects `Dockerfile` and not `Dockerfile.agenta.oss`) Ah, got it....